### What this PR does / why we need it?
Rename `_910B` to `A2`;
Rename `_910_93` to `A3`;
Rename `_910_95` to `A5`;
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: zzzzwwjj <1183291235@qq.com>
### What this PR does / why we need it?
pd disaggregated support cross-machine.
We send the primary and secondary node information of node p to node d.
When node d pulls the KV data, it retrieves the corresponding primary or
secondary node information from the mapping.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
### What this PR does / why we need it?
This PR add `qkv_rmsnorm_rope` operator and introduces a graph fusion
pass for `qknorm_rope` operations. The implementation includes a new
configuration flag, a pattern matching pass using
`torch._inductor.pattern_matcher`, and a custom Triton kernel for the
fused operation.
Co-authored-by: Angazenn
[supperccell@163.com](mailto:supperccell@163.com)
### Does this PR introduce _any_ user-facing change?
Yes, add new additional_config
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wxsIcey <1790571317@qq.com>
### What this PR does / why we need it?
We refactored the eagle_proposer.py to adapt the framework of eagle.py
in vllm-v0.12.0, to support the logit of padded drafter batch and
async-scheduler.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: anon189Ty <Stari_Falcon@outlook.com>
Co-authored-by: drslark <slarksblood@qq.com>
### What this PR does / why we need it?
(1)refactor npu_model_runner for profile_run
(2) move _select_moe_comm_method to ascend_forward_context
(3) delete _init_model_kwargs in npu_model_runner
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Na
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Signed-off-by: zhenwenqi2024 <155598497+zhenwenqi2024@users.noreply.github.com>
### What this PR does / why we need it?
When use mtp, full decdoe only and async_scheduling together, finding a
input err for FIA ops due to the non-increasing input
of the 'actual_seq_lengths'. This bug is caused by the filling the
variable ‘query_start_loc’. We need to fill the query_start_loc' s end
by the 'cu_num_tokens' instead of '-1'
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: hust17yixuan <303660421@qq.com>
### What this PR does / why we need it?
this pr removes apply_gramme in npu_model_runner. we change logits to
cpu, and do the same thing with gpu_model_runner.
it may change the performance, we will change it after torch.compile is
supported with npu inductor
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
### What this PR does / why we need it?
Currently, we are using `AscendRejctionSampler` that extends from
`RejctionSampler` in spec decoding. `AscendRejctionSampler` override
`forward` of `RejctionSampler`, only aming to replace `rejection_sample`
func. This
causes a lot of code of `RejctionSampler` cannot be reused, for example:
- https://github.com/vllm-project/vllm/pull/19482
- https://github.com/vllm-project/vllm/pull/26060
- https://github.com/vllm-project/vllm/pull/29223
#### Proposed Change:
- Delete `AscendRejctionSampler` and use `RejctionSampler` directly in
model runner.
- Patch `RejctionSampler.expand_batch_to_tokens` and
`RejctionSampler.rejection_sample`, maybe a better way is to make them
as custom ops.
- Modify `NPUModelRunner` following
https://github.com/vllm-project/vllm/pull/26060
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- [x] test logits processor for spec decoding
- [x] test logprobs for spec decoding
- [x] test logprobs for spec decoding + async shcheduling (test with
https://github.com/vllm-project/vllm-ascend/pull/4893/)
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
### What this PR does / why we need it?
The fused alltoall operator itself was not designed or implemented to
handle the scenario where tensors are lists, but the weights for dynamic
load balancing are in list form.
Therefore, we have disabled this operator when using dynamic load
balancing.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: shenchuxiaofugui <1311027364@qq.com>
### What this PR does / why we need it?
Fix the bug " TypeError: 'NoneType' object is not iterable' " in
vllm_ascend/compilation/acl_graph.py
The reason of that is the attn_metadata is none in the dummy_run of MTP.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: chenmenglong <chenmenglong1@huawei.com>
The `attn_metadata` is not used by any draft proposer, so we can remove
it.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
### What this PR does / why we need it?
Fix the incorrect use of python's sum function on PyTorch tensors.
1. Using Python's sum() function on a tensor self.num_pcp_pads resulted
in 6ms execution time
Optimization: replacing with PyTorch's torch.sum() reduced execution
time to 474µs
2. scheduler_output.scheduled_spec_decode_tokens undergoes repeated loop
processing even when speculative decoding is not used
Optimization: added conditional logic to skip processing loops when
speculative decoding is disabled, eliminating unnecessary computational
overhead.
- vLLM version: 86e178f7c4d8c3b0eaf3c8e3f810a83f63b90e24
- vLLM main:
86e178f7c4
Signed-off-by: wangx700 <wangxin700@huawei.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
### What this PR does / why we need it?
Corrects attention metadata size for MTP when both asynchronous
scheduling and full ACL graph mode are enabled. This prevents potential
size mismatches during execution.
Additionally, improves the robustness of calculating token sample
indices by explicitly aligning tensor shapes.
Finally, prevents padding when the number of input tokens exceeds the
maximum ACL graph batch size to avoid out-of-bounds errors.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
Need to add corresponding test case ASAP.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Signed-off-by: Yizhou <136800916+yiz-liu@users.noreply.github.com>
Co-authored-by: Jade Zheng <zheng.shoujian@outlook.com>
pick from https://github.com/vllm-project/vllm-ascend/pull/4736 to fix
the merge conflict
### What this PR does / why we need it?
Currently, the all_reduce operation in _sync_metadata_across_dp is
performed with gloo backend which is extremely time-consuming when
DPEngineCores are in different nodes. This operation cannot be ignored
by async scheduling in multi-node-scenarios with speculative decoding
(e.g., EAGLE, mtp).
This pr eliminates the all_reduce operation for D Nodes and change the
input parameter of MoEDispatch & MoeCombine operators to make MC2EP
support different num_tokens across all ranks.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Tested with PD disaggregation (2P: DP2TP8EP16 1D: DP8TP4EP32) scenarios
while enabling async scheduling. This pr can remove cross-node
all_reduce with gloo backend and further reduce latency with correct
accuracy.
---------
Signed-off-by: linfeng-yuan <1102311262@qq.com>
Co-authored-by: linfeng-yuan <1102311262@qq.com>
### What this PR does / why we need it?
now vllm-ascend uses AsyncGPUModelRunnerOutput
,AsyncNPUModelRunnerOutput before is outdated, so we should fix it
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
### What this PR does / why we need it?
The newest version crashes in PD separation scenarios because the
function is missing the `vllm_config` parameter.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: Jade Zheng <zheng.shoujian@outlook.com>
### What this PR does / why we need it?
refactor npu_modelrunner， we should be close to gpu_modelrunner
### Does this PR introduce _any_ user-facing change?
NO
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Signed-off-by: zhenwenqi2024 <155598497+zhenwenqi2024@users.noreply.github.com>
### What this PR does / why we need it?
vllm-ascend support Ascend950 with Qwen dense model
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangyao <iwangyao@outlook.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
mindie_turbo is out of data for long time. This PR remove the related register method.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This PR clean up useless torchair logic in model runner. The moge doc is
only for torchair, it can be removed as well.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
VLLM_ASCEND_ENABLE_TOPK_TOPP_OPTIMIZATION is enabled by default for long
time. Let's remove it now.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
This PR eliminates the simplicit HD synchronization in sfa backend, and
_build_dummy_attn_metadata and dummy_run in mtp_proposer, significantly
improving dsv3.2 performance in low-latency scenarios.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Performance improvements are observed with E2E performance serving (P:
DP4TP8EP32 D: DP8TP4EP32) with `num_speculative_tokens=3`.
DSV3.2-W8A8-EXP:
TPOT: 41.67ms -> 23.36ms
ITL: 85.93ms -> 55.96ms
DSV3.2-W8A8 (relaesed in December):
TPOT: 18.11ms
ITL: 56.13ms
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: linfeng-yuan <1102311262@qq.com>
### What this PR does / why we need it?
We introduced the npugraph_ex backend through the vllm's adaptor
dispatch mechanism to accelerate aclgraph. This solution is based on
torch.compile and uses torchair to optimize the fx.graph. The
performance gains are mainly obtained from the static kernel. We
conducted tests on Qwen3-30B and achieved over 5% performance
optimization.
### Does this PR introduce _any_ user-facing change?
Yes, we add a new switch named"enable_npugraph_ex" in additional_config,
default is False.
We also add an example to show how to register custom replacement pass
### More information about this PR
This feature depends on the release of CANN and torch_npu in Q4.
We tested it on a package that has not been publicly released yet and
verified that the functionality works.
This feature is still experimental at the moment; setting the config
true will directly raise error.
Merging into the main branch initially involves some preliminary commits
to facilitate subsequent development and testing of the feature, as well
as to avoid submitting an excessively large PR at once.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: chencangtao <chencangtao@huawei.com>
Signed-off-by: ChenCangtao <50493711+ChenCangtao@users.noreply.github.com>
Co-authored-by: chencangtao <chencangtao@huawei.com>
Co-authored-by: panchao-hub <315134829@qq.com>
Co-authored-by: wbigat <wbigat@163.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
### What this PR does / why we need it?
The first commit support `FULL_DECODE_ONLY`:
- Update `AscendSFAMetadataBuilder` to use `num_input_tokens` for
slicing slots and positions, ensuring fixed tensor shapes.
- Implement padding logic for `query_start_loc` in `NPUModelRunner` to
support uniform decode in full graph mode, aligning with GPU runner
behavior.
- Adjust MLA cosine cache allocation to occur independently of graph
mode and switch to using device-resident sequence lengths for attention
metadata.
- Remove redundant slicing of hidden states and outputs in
`AscendSFAImpl` and optimize `sin`/`cos` cache updates.
The second commit take MTP into account:
- Update `AscendSFAMetadataBuilder` to use `num_input_tokens` for
slicing slots and positions, ensuring fixed tensor shapes.
- Implement padding logic for `query_start_loc` in `NPUModelRunner` to
support uniform decode in full graph mode, aligning with GPU runner
behavior.
- Adjust MLA cosine cache allocation to occur independently of graph
mode and switch to using device-resident sequence lengths for attention
metadata.
- Remove redundant slicing of hidden states and outputs in
`AscendSFAImpl` and optimize `sin`/`cos` cache updates.
And the rest of them are just bugfix.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
Test cases needed.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
### What this PR does / why we need it?
The logprobs_tensor was not initialized before accessing its token_id
member, leading to a crash when tokenizer.decode() is called by passing
a negative token_id
### How was this patch tested?
Constructed an inference request with two prompts and set
SamplingParams(prompt_logprobs=<non-None value>) (e.g.,
prompt_logprobs=1).
After applying the fix (proper initialization of logprobs_tensor), the
same request completed successfully without errors, and the returned
logprobs matched expected values.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: jiangweixiang <jwx02384838@antgroup.com>
Co-authored-by: jiangweixiang <jwx02384838@antgroup.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
### What this PR does / why we need it?
To support pipeline parallel with PD disaggregation, this PR support PP
in mooncake connector and fix other bugs when enable pp with other
optimization params, including following changes:
- mooncake connector support pp in prefill, we do not support decode pp
currently
- fix bugs when enable both pp and flashcomm1
- optimize ascend-scheduler to support full batch in multiple pipeline
stages, original implementation would cause all pipeline stages
batch_size total summed to max_num_seq, which makes pipeline is not
full, this optimization can make all stages running with full batch_size
= max_num_seq, the same changes will contribute to vllm scheduler too.
### Does this PR introduce _any_ user-facing change?
add `pp_size` in mooncake connector kv_connector_extra_config
```
"kv_connector_extra_config": {
"use_ascend_direct": true,
"prefill": {
"dp_size": 1,
"tp_size": 4,
"pp_size": 4
},
"decode": {
"dp_size": 16,
"tp_size": 1
}
}
```
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: chenxiao <Jaychou1620@Gmail.com>
Signed-off-by: Kurumi5210 <Jaychou1620@Gmail.com>
Signed-off-by: Kurumi5210 <jaychou1620@gmail.com>
Signed-off-by: 秋刀鱼 <jaychou1620@Gmail.com>
Co-authored-by: chenxiao <Jaychou1620@Gmail.com>
Co-authored-by: zss <zss@qq.com>
Co-authored-by: zss <3265779424@qq.com>
### What this PR does / why we need it?
Adds W4A16 quantization method for the Kimi-K2-Thinking model and
updates relevant modules to support the new quantization method.
- Implements complete W4A16 quantization method including weight
packing/unpacking, per-group quantization parameter generation,
post-processing logic and MoE method application.
- Adds parameters `use_int4_w4a16`, `w1_offset` and `w2_offset`, adjusts
`with_quant` conditional logic to support W4A16 matrix multiplication.
- Adds `packed_modules_model_mapping` for Kimi-K2-Thinking model and
processing logic for `weight_packed` field.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: zhoux77899 <zhouxiang100@huawei.com>
Signed-off-by: Ruri <33858552+zhoux77899@users.noreply.github.com>
Signed-off-by: Ruri <zhouxiang100@huawei.com>
### What this PR does / why we need it?
Support pooling models (like `bge-reranker-v2-m3`) in vllm-ascend, this
pr covered the three model types of embed (cls_token, mean_token,
lasttoken).
After this
[commit](17373dcd93),
vllm has provided support for adapting pooling models on the v1 engine.
This PR includes corresponding adaptations on the vllm-ascend side.
Fixes#1960
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: lianyibo <lianyibo1@kunlunit.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
aclgraph is stable and fast now. Let's drop torchair graph mode now.
TODO: some logic to adapt torchair should be cleaned up as well. We'll
do it in the following PR.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
### What this PR does / why we need it?
As support for the mooncake connector is now available, the llmdatadist
connector is no longer being maintained, so the llmdatadist-related
files need to be retired.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
By ci
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: wangxiaoteng <wangxiaoteng@huawei.com>
Signed-off-by: liziyu <liziyu16@huawei.com>
Co-authored-by: liziyu <liziyu16@huawei.com>
### What this PR does / why we need it?
This PR is to fix a smoking test failure. Adjust mtp_proposer and
model_runner_v1 to route MTP decoding through the non‑fused MoE
implementation while keeping the overall inference flow unchanged.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: mojave2 <chenchen145@huawei.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
### What this PR does / why we need it?
Support pp for kv pool
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: baxingpiaochong <771405853@qq.com>
### What this PR does / why we need it?
In reinforcement learning scenarios, the current inference applies a
transpose operation to the weights. For a cleaner architecture, the
weight transpose module was moved to wakeup.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: lhp-deep <liuhaopeng1@huawei.com>
Co-authored-by: weijinqian0 <1184188277@qq.com>
### What this PR does / why we need it?
Fix dp padding logic in dummyrun. After
https://github.com/vllm-project/vllm/pull/28579, `num_tokens` will be
padded in `CudagraphDispatcher`, thus we also need to do the pad in the
dummy_run.
### How was this patch tested?
Test locally with the following scripts
```bash
VLLM_USE_MODELSCOPE=true python3 -m vllm.entrypoints.openai.api_server \
--model wemaster/deepseek_mtp_main_random_bf16 \
--trust-remote-code \
--data-parallel-size 4 \
--tensor-parallel-size 1 \
--compilation-config '{"cudagraph_capture_sizes":[96],"cudagraph_mode":"FULL_DECODE_ONLY"}' \
--enable-expert-parallel
```
```bash
vllm bench serve --model wemaster/deepseek_mtp_main_random_bf16 --endpoint /v1/completions --dataset-name random --random-input 512 --random-output 100 --num-prompts 48 --request-rate 1 --ready-check-timeout-sec 0
```
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: MengqingCao <cmq0113@163.com>
### What this PR does / why we need it?
Move the logic for adjusting ACL graph capture sizes for speculative
decoding from the generic utility module into a dedicated method within
the compilation configuration.
This change improves code organization and encapsulation by making the
compilation configuration responsible for managing its own state. The
model runner now triggers this adjustment directly, providing the
necessary context.
### Does this PR introduce _any_ user-facing change?
None.
### How was this patch tested?
None.
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
this pr aims to support async_scheduling for mtp, which refer to vllm pr
https://github.com/vllm-project/vllm/pull/24799.
and this pr fix some synchronize problem in vllm-ascend.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
It's safe to drop ascend scheduler now. The related test and doc has
been removed already
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
This PR introduces the Ascend implementation of the
`dispatch_ffn_combine` kernel and wires it into the vLLM-Ascend runtime,
together with follow‑up fixes to ensure the kernel builds and runs
correctly in CI.
- Add full host and device implementation of the `dispatch_ffn_combine`
kernel under `csrc/dispatch_ffn_combine`, including tiling logic, MOE
routing helpers, and kernel utilities for quantized FFN dispatch.
- Integrate the new kernel with the PyTorch binding
(csrc/torch_binding.cpp, csrc/torch_binding_meta.cpp) and the Ascend
runtime (vllm_ascend/ascend_forward_context.py,
vllm_ascend/worker/model_runner_v1.py).
- Extend fused MoE communication and token dispatch support in
`vllm_ascend/ops/fused_moe`, adding methods/utilities needed by the new
dispatch path.
- Update quantization logic in vllm_ascend/quantization/w8a8_dynamic.py
to support the new FFN dispatch flow.
- Fix kernel build issues by adjusting `csrc/build_aclnn.sh`, CMake
configuration, and include/namespace usage in the new kernel files.
- Add an end‑to‑end nightly test
`tests/e2e/nightly/ops/test_dispatch_ffn_combine.py` and helper
utilities in `vllm_ascend/utils.py` to validate the new kernel.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.12.0
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.12.0
---------
Signed-off-by: mojave2 <chenchen145@huawei.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
### What this PR does / why we need it?
Due to the requirement of the FIA operator that the **query.shape[0]**
must match **actual_seq_len[-1]**, in graph mode and multi-DP scenarios,
the query is padded to the size of **num_input_token**. This leads to
validation errors during tiling in the operator. However, since the
padding is applied at the end of the query, it does not affect the
actual execution result of the operator, and the precision remains
unaffected.
<img width="2434" height="49" alt="image"
src="https://github.com/user-attachments/assets/63520816-fbc3-4382-82b9-89dbb1492f6c"
/>
Our modification padding both **actual_seq_len** and
**actual_seq_len_kv** to resolve the validation issue in the operator.
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
### What this PR does / why we need it?
Provide high-performance AscendC operators lightning_indexer and
sparse_flash_attention to boost the execution performance of the
DeepSeek v3.2 model. Meanwhile, adapt the two AscendC operators to
vllm-ascend framework.
### Does this PR introduce _any_ user-facing change?
No (only underlying operator optimizations, with no user-facing changes)
### How was this patch tested?
- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2
Signed-off-by: MingYang119 <songmingyang@huawei.com>
